Liang Zhao

Shipeng Liu, Liang Zhao, Dengfeng Chen et al.

Quantifying and evaluating image complexity can be instrumental in enhancing the performance of various computer vision tasks. Supervised learning can effectively learn image complexity features from well-annotated datasets. However, creating such datasets requires expensive manual annotation costs. The models may learn human subjective biases from it. In this work, we introduce the MoCo v2 framework. We utilize contrastive learning to represent image complexity, named CLIC (Contrastive Learning for Image Complexity). We find that there are complexity differences between different local regions of an image, and propose Random Crop and Mix (RCM), which can produce positive samples consisting of multi-scale local crops. RCM can also expand the train set and increase data diversity without introducing additional data. We conduct extensive experiments with CLIC, comparing it with both unsupervised and supervised methods. The results demonstrate that the performance of CLIC is comparable to that of state-of-the-art supervised methods. In addition, we establish the pipelines that can apply CLIC to computer vision tasks to effectively improve their performance.

Liang Zhao, Zehan Bao, Yi Xie et al.

Recent advances in Gaussian Splatting have significantly advanced the field, achieving both panoptic and interactive segmentation of 3D scenes. However, existing methodologies often overlook the critical need for reconstructing specified targets with complex structures from sparse views. To address this issue, we introduce TSGaussian, a novel framework that combines semantic constraints with depth priors to avoid geometry degradation in challenging novel view synthesis tasks. Our approach prioritizes computational resources on designated targets while minimizing background allocation. Bounding boxes from YOLOv9 serve as prompts for Segment Anything Model to generate 2D mask predictions, ensuring semantic accuracy and cost efficiency. TSGaussian effectively clusters 3D gaussians by introducing a compact identity encoding for each Gaussian ellipsoid and incorporating 3D spatial consistency regularization. Leveraging these modules, we propose a pruning strategy to effectively reduce redundancy in 3D gaussians. Extensive experiments demonstrate that TSGaussian outperforms state-of-the-art methods on three standard datasets and a new challenging dataset we collected, achieving superior results in novel view synthesis of specific objects. Code is available at: https://github.com/leon2000-ai/TSGaussian.

Wenhao fan, Liang Zhao, Jiayang Wang et al.

Android is currently the most extensively used smartphone platform in the world. Due to its popularity and open source nature, Android malware has been rapidly growing in recent years, and bringing great risks to users' privacy. The malware applications in a malware family may have common features and similar behaviors, which are beneficial for malware detection and inspection. Thus, classifying Android malware into their corresponding families is an important task in malware analysis. At present, the main problem of existing research works on Android malware family classification lies in that the extracted features are inadequate to represent the common behavior characteristics of the malware in malicious families, and leveraging a single classifier or a static ensemble classifier is restricted to further improve the accuracy of classification. In this paper, we propose FamDroid, a learning-based Android malware family classification scheme using static analysis technology. In FamDroid, the explicit features including permissions, hardware components, app components, intent filters are extracted from the apk files of a malware application. Besides, a hidden feature generated from the extracted APIs is used to represents the API call relationship in the application. Then, we design an adaptive weighted ensemble classifier, which considers the adaptability of the sample to each base classifier, to carry out accurate malware family classification. We conducted experiments on the Drebin dataset which contains 5560 Android malicious applications. The superiority of FamDroid is demonstrated through comparing it with 5 traditional machine learning models and 4 state-of-the-art reference schemes. FamDroid can correctly classify 98.92% of malware samples into their families and achieve 99.12% F1-Score.

Renato Tinós, Liang Zhao, Francisco Chicano et al.

The NK hybrid genetic algorithm for clustering is proposed in this paper. In order to evaluate the solutions, the hybrid algorithm uses the NK clustering validation criterion 2 (NKCV2). NKCV2 uses information about the disposition of $N$ small groups of objects. Each group is composed of $K+1$ objects of the dataset. Experimental results show that density-based regions can be identified by using NKCV2 with fixed small $K$. In NKCV2, the relationship between decision variables is known, which in turn allows us to apply gray box optimization. Mutation operators, a partition crossover, and a local search strategy are proposed, all using information about the relationship between decision variables. In partition crossover, the evaluation function is decomposed into $q$ independent components; partition crossover then deterministically returns the best among $2^q$ possible offspring with computational complexity $O(N)$. The NK hybrid genetic algorithm allows the detection of clusters with arbitrary shapes and the automatic estimation of the number of clusters. In the experiments, the NK hybrid genetic algorithm produced very good results when compared to another genetic algorithm approach and to state-of-art clustering algorithms.

Yawen Chen, Jiande Sun, Jinhui Wang et al.

Student performance prediction is one of the most important subjects in educational data mining. As a modern technology, machine learning offers powerful capabilities in feature extraction and data modeling, providing essential support for diverse application scenarios, as evidenced by recent studies confirming its effectiveness in educational data mining. However, despite extensive prediction experiments, machine learning methods have not been effectively integrated into practical teaching strategies, hindering their application in modern education. In addition, massive features as input variables for machine learning algorithms often leads to information redundancy, which can negatively impact prediction accuracy. Therefore, how to effectively use machine learning methods to predict student performance and integrate the prediction results with actual teaching scenarios is a worthy research subject. To this end, this study integrates the results of machine learning-based student performance prediction with tiered instruction, aiming to enhance student outcomes in target course, which is significant for the application of educational data mining in contemporary teaching scenarios. Specifically, we collect original educational data and perform feature selection to reduce information redundancy. Then, the performance of five representative machine learning methods is analyzed and discussed with Random Forest showing the best performance. Furthermore, based on the results of the classification of students, tiered instruction is applied accordingly, and different teaching objectives and contents are set for all levels of students. The comparison of teaching outcomes between the control and experimental classes, along with the analysis of questionnaire results, demonstrates the effectiveness of the proposed framework.

Hassan Hamad, Yingru Xu, Liang Zhao et al.

Tool-augmented large language models (LLMs) are increasingly employed in real-world applications, but tool usage errors still hinder their reliability. We introduce ToolCritic, a diagnostic framework that evaluates and improves LLM behavior in multi-turn, tool-augmented dialogues. ToolCritic detects eight distinct error types specific to tool-calling (e.g., premature invocation, argument misalignment, and misinterpretation of tool outputs) and provides targeted feedback to the main LLM. The main LLM, assumed to have strong reasoning, task understanding and orchestration capabilities, then revises its response based on ToolCritic's feedback. We systematically define these error categories and construct a synthetic dataset to train ToolCritic. Experimental results on the Schema-Guided Dialogue (SGD) dataset demonstrate that ToolCritic improves tool-calling accuracy by up to 13% over baselines, including zero-shot prompting and self-correction techniques. This represents a promising step toward more robust LLM integration with external tools in real-world dialogue applications.

Tianwen Wei, Bo Zhu, Liang Zhao et al.

In this technical report, we introduce the training methodologies implemented in the development of Skywork-MoE, a high-performance mixture-of-experts (MoE) large language model (LLM) with 146 billion parameters and 16 experts. It is initialized from the pre-existing dense checkpoints of our Skywork-13B model. We explore the comparative effectiveness of upcycling versus training from scratch initializations. Our findings suggest that the choice between these two approaches should consider both the performance of the existing dense checkpoints and the MoE training budget. We highlight two innovative techniques: gating logit normalization, which improves expert diversification, and adaptive auxiliary loss coefficients, allowing for layer-specific adjustment of auxiliary loss coefficients. Our experimental results validate the effectiveness of these methods. Leveraging these techniques and insights, we trained our upcycled Skywork-MoE on a condensed subset of our SkyPile corpus. The evaluation results demonstrate that our model delivers strong performance across a wide range of benchmarks.

Esteban Wilfredo Vilca Zuñiga, Liang Zhao

High-level classification algorithms focus on the interactions between instances. These produce a new form to evaluate and classify data. In this process, the core is a complex network building methodology. The current methodologies use variations of kNN to produce these graphs. However, these techniques ignore some hidden patterns between attributes and require normalization to be accurate. In this paper, we propose a new methodology for network building based on attribute-attribute interactions that do not require normalization. The current results show us that this approach improves the accuracy of the high-level classification algorithm based on betweenness centrality.

Esteban Vilca, Liang Zhao

Data classification is a major machine learning paradigm, which has been widely applied to solve a large number of real-world problems. Traditional data classification techniques consider only physical features (e.g., distance, similarity, or distribution) of the input data. For this reason, those are called \textit{low-level} classification. On the other hand, the human (animal) brain performs both low and high orders of learning and it has a facility in identifying patterns according to the semantic meaning of the input data. Data classification that considers not only physical attributes but also the pattern formation is referred to as \textit{high-level} classification. Several high-level classification techniques have been developed, which make use of complex networks to characterize data patterns and have obtained promising results. In this paper, we propose a pure network-based high-level classification technique that uses the betweenness centrality measure. We test this model in nine different real datasets and compare it with other nine traditional and well-known classification models. The results show us a competent classification performance.

Fabricio A Breve, Marcos G Quiles, Liang Zhao et al.

Object selection refers to the mechanism of extracting objects of interest while ignoring other objects and background in a given visual scene. It is a fundamental issue for many computer vision and image analysis techniques and it is still a challenging task to artificial visual systems. Chaotic phase synchronization takes place in cases involving almost identical dynamical systems and it means that the phase difference between the systems is kept bounded over the time, while their amplitudes remain chaotic and may be uncorrelated. Instead of complete synchronization, phase synchronization is believed to be a mechanism for neural integration in brain. In this paper, an object selection model is proposed. Oscillators in the network representing the salient object in a given scene are phase synchronized, while no phase synchronization occurs for background objects. In this way, the salient object can be extracted. In this model, a shift mechanism is also introduced to change attention from one object to another. Computer simulations show that the model produces some results similar to those observed in natural vision systems.

Fabricio Aparecido Breve, Liang Zhao, Marcos Gonçalves Quiles

Semi-supervised learning methods are usually employed in the classification of data sets where only a small subset of the data items is labeled. In these scenarios, label noise is a crucial issue, since the noise may easily spread to a large portion or even the entire data set, leading to major degradation in classification accuracy. Therefore, the development of new techniques to reduce the nasty effects of label noise in semi-supervised learning is a vital issue. Recently, a graph-based semi-supervised learning approach based on Particle competition and cooperation was developed. In this model, particles walk in the graphs constructed from the data sets. Competition takes place among particles representing different class labels, while the cooperation occurs among particles with the same label. This paper presents a new particle competition and cooperation algorithm, specifically designed to increase the robustness to the presence of label noise, improving its label noise tolerance. Different from other methods, the proposed one does not require a separate technique to deal with label noise. It performs classification of unlabeled nodes and reclassification of the nodes affected by label noise in a unique process. Computer simulations show the classification accuracy of the proposed method when applied to some artificial and real-world data sets, in which we introduce increasing amounts of label noise. The classification accuracy is compared to those achieved by previous particle competition and cooperation algorithms and other representative graph-based semi-supervised learning methods using the same scenarios. Results show the effectiveness of the proposed method.

Filipe Alves Neto Verri, Renato Tinós, Liang Zhao

Data and knowledge representation are fundamental concepts in machine learning. The quality of the representation impacts the performance of the learning model directly. Feature learning transforms or enhances raw data to structures that are effectively exploited by those models. In recent years, several works have been using complex networks for data representation and analysis. However, no feature learning method has been proposed for such category of techniques. Here, we present an unsupervised feature learning mechanism that works on datasets with binary features. First, the dataset is mapped into a feature--sample network. Then, a multi-objective optimization process selects a set of new vertices to produce an enhanced version of the network. The new features depend on a nonlinear function of a combination of preexisting features. Effectively, the process projects the input data into a higher-dimensional space. To solve the optimization problem, we design two metaheuristics based on the lexicographic genetic algorithm and the improved strength Pareto evolutionary algorithm (SPEA2). We show that the enhanced network contains more information and can be exploited to improve the performance of machine learning methods. The advantages and disadvantages of each optimization strategy are discussed.

Filipe Alves Neto Verri, Paulo Roberto Urio, Liang Zhao

The emergence of collective dynamics in neural networks is a mechanism of the animal and human brain for information processing. In this paper, we develop a computational technique using distributed processing elements in a complex network, which are called particles, to solve semi-supervised learning problems. Three actions govern the particles' dynamics: generation, walking, and absorption. Labeled vertices generate new particles that compete against rival particles for edge domination. Active particles randomly walk in the network until they are absorbed by either a rival vertex or an edge currently dominated by rival particles. The result from the model evolution consists of sets of edges arranged by the label dominance. Each set tends to form a connected subnetwork to represent a data class. Although the intrinsic dynamics of the model is a stochastic one, we prove there exists a deterministic version with largely reduced computational complexity; specifically, with linear growth. Furthermore, the edge domination process corresponds to an unfolding map in such way that edges "stretch" and "shrink" according to the vertex-edge dynamics. Consequently, the unfolding effect summarizes the relevant relationships between vertices and the uncovered data classes. The proposed model captures important details of connectivity patterns over the vertex-edge dynamics evolution, in contrast to previous approaches which focused on only vertex or only edge dynamics. Computer simulations reveal that the new model can identify nonlinear features in both real and artificial data, including boundaries between distinct classes and overlapping structures of data.

Leonardo N. Ferreira, Liang Zhao

In this paper, we propose a technique for time series clustering using community detection in complex networks. Firstly, we present a method to transform a set of time series into a network using different distance functions, where each time series is represented by a vertex and the most similar ones are connected. Then, we apply community detection algorithms to identify groups of strongly connected vertices (called a community) and, consequently, identify time series clusters. Still in this paper, we make a comprehensive analysis on the influence of various combinations of time series distance functions, network generation methods and community detection techniques on clustering results. Experimental study shows that the proposed network-based approach achieves better results than various classic or up-to-date clustering techniques under consideration. Statistical tests confirm that the proposed method outperforms some classic clustering algorithms, such as $k$-medoids, diana, median-linkage and centroid-linkage in various data sets. Interestingly, the proposed method can effectively detect shape patterns presented in time series due to the topological structure of the underlying network constructed in the clustering process. At the same time, other techniques fail to identify such patterns. Moreover, the proposed method is robust enough to group time series presenting similar pattern but with time shifts and/or amplitude variations. In summary, the main point of the proposed method is the transformation of time series from time-space domain to topological domain. Therefore, we hope that our approach contributes not only for time series clustering, but also for general time series analysis tasks.

Lucas Antiqueira, Liang Zhao

Models of neural networks have proven their utility in the development of learning algorithms in computer science and in the theoretical study of brain dynamics in computational neuroscience. We propose in this paper a spatial neural network model to analyze the important class of functional networks, which are commonly employed in computational studies of clinical brain imaging time series. We developed a simulation framework inspired by multichannel brain surface recordings (more specifically, EEG -- electroencephalogram) in order to link the mesoscopic network dynamics (represented by sampled functional networks) and the microscopic network structure (represented by an integrate-and-fire neural network located in a 3D space -- hence the term spatial neural network). Functional networks are obtained by computing pairwise correlations between time-series of mesoscopic electric potential dynamics, which allows the construction of a graph where each node represents one time-series. The spatial neural network model is central in this study in the sense that it allowed us to characterize sampled functional networks in terms of what features they are able to reproduce from the underlying spatial network. Our modeling approach shows that, in specific conditions of sample size and edge density, it is possible to precisely estimate several network measurements of spatial networks by just observing functional samples.

Thiago Christiano Silva, Liang Zhao

Complex networks refer to large-scale graphs with nontrivial connection patterns. The salient and interesting features that the complex network study offer in comparison to graph theory are the emphasis on the dynamical properties of the networks and the ability of inherently uncovering pattern formation of the vertices. In this paper, we present a hybrid data classification technique combining a low level and a high level classifier. The low level term can be equipped with any traditional classification techniques, which realize the classification task considering only physical features (e.g., geometrical or statistical features) of the input data. On the other hand, the high level term has the ability of detecting data patterns with semantic meanings. In this way, the classification is realized by means of the extraction of the underlying network's features constructed from the input data. As a result, the high level classification process measures the compliance of the test instances with the pattern formation of the training data. Out of various high level perspectives that can be utilized to capture semantic meaning, we utilize the dynamical features that are generated from a tourist walker in a networked environment. Specifically, a weighted combination of transient and cycle lengths generated by the tourist walk is employed for that end. Interestingly, our study shows that the proposed technique is able to further improve the already optimized performance of traditional classification techniques.